Sinbad-The-Sailor / Model details
Qwen3.5-4B-NSFW-ARA-Heretic-Literotica-i1-GGUF
Sinbad-The-Sailor/Qwen3.5-4B-NSFW-ARA-Heretic-Literotica-i1-GGUF
About this model
Sinbad-The-Sailor's GGUF release of Sinbad-The-Sailor/Qwen3.5-4B-NSFW-ARA-Heretic-Literotica, a model the creator describes as built on the Qwen 3.5 architecture with 4B parameters and designed for immersive erotic storytelling and creative prose. The creator says the base model inherits the technical uncensorship approaches of the ARA and Heretic frameworks, and this repository provides versions quantized with an Importance Matrix (Imatrix) to reduce perplexity and preserve knowledge compared to standard quantization. Available files include Q4_K_M, Q5_K_M, and Q6_K quantizations. The model card states it is intended for adult audiences and generates explicit NSFW content without artificial refusal. The metadata lists GGUF as the format and no license. The creator's claims about Imatrix benefits and uncensored behavior have not been independently tested here.
Description sources
Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.
Size and formats
- Base model
- Sinbad-The-Sailor/Qwen3.5-4B-NSFW-ARA-Heretic-Literotica
- Parameters
- Unknown
- Main repository formats
- GGUF
- License tag
- Unknown
- Languages
- en
- Last updated
- 2026-03-25 · 13:45:59.000 UTC
What changed
Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.
- uncensoredsource tag:
uncensored
Family evidence
These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.
- Qwen: Base model: Sinbad-The-Sailor/Qwen3.5-4B-NSFW-ARA-Heretic-Literotica
Available versions
Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.
- Main repository files ↗GGUF
- No other explicitly linked versions recorded.
Customize or build on this model
Listed from public GitHub data, not tested by us. Read the code and license before you run anything.
Tools to customize it further
Make a smaller download (quantize)
- llama.cpp ↗ ★ 132,124
Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.
Learn the techniques
- LLM Course ↗ ★ 84,633
A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.
Source provenance
- Downloads
- 9,617
- Likes
- 53
- Metadata checked
- 2026-10-24 · 08:12:56 UTC
- First seen in index
- 2026-10-24 · 08:12:56 UTC
- Source revision
- f9d8d1123e2875c9edba13220e28b1a774b008df
Source-card excerpt
Source model card excerpt: Qwen3.5-4B-NSFW-ARA-Heretic-Literotica-i1-GGUF The i1 release introduces models quantized with an Importance Matrix, significantly improving performance on key prompt structures. Overview This repository contains GGUF (GPT-Generated
From Sinbad-The-Sailor/Qwen3.5-4B-NSFW-ARA-Heretic-Literotica-i1-GGUF. Creator model-card excerpt, not an independent review.
Inspect before you run
Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.
This directory does not run, host, redistribute, or test model weights.
Collection rules & limitations ↗